mm: enable maple tree RCU mode by default.

commit 3dd4432549415f3c65dd52d5c687629efbf4ece1 upstream.

Use the maple tree in RCU mode for VMA tracking.

The maple tree tracks the stack and is able to update the pivot
(lower/upper boundary) in-place to allow the page fault handler to write
to the tree while holding just the mmap read lock.  This is safe as the
writes to the stack have a guard VMA which ensures there will always be
a NULL in the direction of the growth and thus will only update a pivot.

It is possible, but not recommended, to have VMAs that grow up/down
without guard VMAs.  syzbot has constructed a testcase which sets up a
VMA to grow and consume the empty space.  Overwriting the entire NULL
entry causes the tree to be altered in a way that is not safe for
concurrent readers; the readers may see a node being rewritten or one
that does not match the maple state they are using.

Enabling RCU mode allows the concurrent readers to see a stable node and
will return the expected result.

Link: https://lkml.kernel.org/r/20230227173632.3292573-9-surenb@google.com
Cc: stable@vger.kernel.org
Fixes: d4af56c5c7c6 ("mm: start tracking VMAs with maple tree")
Signed-off-by: Liam R. Howlett <Liam.Howlett@oracle.com>
Reported-by: syzbot+8d95422d3537159ca390@syzkaller.appspotmail.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 500e536..247aedb 100644 (file)
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -725,7 +725,8 @@ struct mm_struct {
        unsigned long cpu_bitmap[];
 };
 
-#define MM_MT_FLAGS    (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN)
+#define MM_MT_FLAGS    (MT_FLAGS_ALLOC_RANGE | MT_FLAGS_LOCK_EXTERN | \
+                        MT_FLAGS_USE_RCU)
 extern struct mm_struct init_mm;
 
 /* Pointer magic because the dynamic array size confuses some compilers. */

diff --git a/kernel/fork.c b/kernel/fork.c
index a6d243a..ec913b1 100644 (file)
--- a/kernel/fork.c
+++ b/kernel/fork.c
@@ -617,6 +617,7 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
        if (retval)
                goto out;
 
+       mt_clear_in_rcu(mas.tree);
        mas_for_each(&old_mas, mpnt, ULONG_MAX) {
                struct file *file;
 
@@ -703,6 +704,8 @@ static __latent_entropy int dup_mmap(struct mm_struct *mm,
        retval = arch_dup_mmap(oldmm, mm);
 loop_out:
        mas_destroy(&mas);
+       if (!retval)
+               mt_set_in_rcu(mas.tree);
 out:
        mmap_write_unlock(mm);
        flush_tlb_mm(oldmm);

diff --git a/mm/mmap.c b/mm/mmap.c
index 1777148..fe1db60 100644 (file)
--- a/mm/mmap.c
+++ b/mm/mmap.c
@@ -2308,7 +2308,7 @@ do_mas_align_munmap(struct ma_state *mas, struct vm_area_struct *vma,
        int count = 0;
        int error = -ENOMEM;
        MA_STATE(mas_detach, &mt_detach, 0, 0);
-       mt_init_flags(&mt_detach, MT_FLAGS_LOCK_EXTERN);
+       mt_init_flags(&mt_detach, mas->tree->ma_flags & MT_FLAGS_LOCK_MASK);
        mt_set_external_lock(&mt_detach, &mm->mmap_lock);
 
        if (mas_preallocate(mas, vma, GFP_KERNEL))
@@ -3095,6 +3095,7 @@ void exit_mmap(struct mm_struct *mm)
         */
        set_bit(MMF_OOM_SKIP, &mm->flags);
        mmap_write_lock(mm);
+       mt_clear_in_rcu(&mm->mm_mt);
        free_pgtables(&tlb, &mm->mm_mt, vma, FIRST_USER_ADDRESS,
                      USER_PGTABLES_CEILING);
        tlb_finish_mmu(&tlb);